Detecting unobserved confounders is crucial for reliable causal inference in observational studies. Existing methods require either linearity assumptions or multiple heterogeneous environments, limiting applicability to nonlinear single-environment settings. To bridge this gap, we propose Kernel Regression Confounder Detection (KRCD), a novel method for detecting unobserved confounding in nonlinear observational data under single-environment conditions. KRCD leverages reproducing kernel Hilbert spaces to model complex dependencies. By comparing standard and higher-order kernel regressions, we derive a test statistic whose significant deviation from zero indicates unobserved confounding. Theoretically, we prove two key results: First, in infinite samples, regression coefficients coincide if and only if no unobserved confounders exist. Second, finite-sample differences converge to zero-mean Gaussian distributions with tractable variance. Extensive experiments on synthetic benchmarks and the Twins dataset demonstrate that KRCD not only outperforms existing baselines but also achieves superior computational efficiency.

Recent advances in multi-agent Large Language Model-based code generation enable collaborative software development through role-specialized agents. However, failure localization of code generation remains challenging due to inter-agent dependencies and solution-path multiplicity. Consequently, existing prompting-based localization methods exhibit vulnerability towards semantically valid but non-canonical strategies. To address this, we propose FLKR (Failure Localization via Knowledge-guided Reasoning), an self-supervised framework that combines behavior encoding, knowledge-strategy alignment, and consistency scoring for solution-path invariant localization. To evaluate, we also introduce COFL (Code Oriented Failure Localization), the first expert-annotated benchmark for fine-grained failure localization. Experiments show FLKR outperforms state-of-the-art prompting-based baselines by up to 14 points in Fault Localization Accuracy and 45 points in Top-1 accuracy, with strong performance in divergent, real-world, and refinement-critical cases. Such results demonstrate that our proposed FLKR generalizes well to real-world software development scenarios and opens up a new direction for failure-aware refinement recommendation by providing precise and interpretable responsibility signals.

Strategic machine learning investigates scenarios where agents manipulate their features to receive favorable decisions from predictive models. To address fairness concerns intrinsic to strategic classification, recent work has introduced group-specific fairness constraints. However, current fairness-aware approaches face a fundamental dilemma in the issue of fairness exposure: making these constraints public enables strategic manipulation and can lead to fairness reversal, while keeping them hidden may reduce social welfare and discourage genuine improvement. To fill this gap, we subsequently propose the problem of Partial Fairness Awareness (PFA), as our theoretical analysis informs that such a dilemma can be mitigated by releasing the candidate set of fairness constraints and concealing the grounding constraint. To be specific, we introduce a belief-guided strategic mechanism wherein agents iteratively interact with the decision system and maintain a belief distribution over the candidate set of fairness constraints. This belief-guided process enables agents, through iterative interaction and feedback, to update their belief distribution over the candidate set, thereby gradually aligning their belief with the grounding fairness constraint employed by the system. Extensive experiments on real-world and synthetic datasets demonstrate that PFA achieves lower group fairness gaps, higher acceptance of truly qualified individuals, and more stable outcomes compared to fully public or private fairness regimes.

Subgraph matching is a well-known NP-hard problem widely applied in fields such as bioinformatics, cheminformatics, and social network analysis. It aims to enumerate all embeddings in a data graph that are isomorphic to a query graph. Subgraph matching algorithms can be roughly classified into BFS-based and DFS-based algorithms. The intersection operation is the core operation in both types of algorithms and consumes a significant amount of time. There are numerous repeated intersection operations in subgraph matching, and their results can be reused. Recent studies have focused on implementing the DFS-based algorithm on GPUs with an explicit stack. We categorize the reuse in the DFS-based algorithm into two types: within-stack reuse and across-stack reuse. Previous works only considered within-stack reuse, which has a narrow scope of application and lacks generality for some query graphs. In this paper, we are the first to propose a method for across-stack reuse in DFS-based algorithms on GPUs. We introduce a tree-structured copy stack to reuse duplicate intersections and design a secondary checking mechanism to ensure the correctness of the reuse. We use the non-blocking lock mechanism to avoid read-write races and conduct a rigorous theoretical analysis to prove that the impact of the non-blocking lock on reuse is negligible. Moreover, we propose a GPU-specific optimization method that uses key nodes to reduce memory transactions during intersection operations. Compared with the state-of-the-art DFS-based matching algorithms, our work achieves $1.12 \times$ to $1.95 \times$ speedup, and the reuse rate reaches 78.68%.ACM Reference Format:Chen Chen, Shanzhi Gu, Junsheng Chang, and Li Shen. 2025. Accelerating DFS-based Subgraph Matching on GPU via Reusing Intersection. In. ACM, New York, NY, USA, 12 pages. https://doi.org/10.1145/nnnnnnn.nnnnnnnn

Code comment, i.e., the natural language text to describe code, is considered as a killer for program comprehension. Current literature approaches mainly focus on comment generation or comment update, and thus fall short on explaining which part of the code leads to a specific content in the comment. In this paper, we propose that addressing such a challenge can better facilitate code understanding. We propose Fosterer, which can build fine-grained semantic interactions between code statements and comment tokens. It not only leverages the advanced deep learning techniques like cross-modal learning and contrastive learning, but also borrows the weapon of pre-trained vision models. Specifically, it mimics the comprehension practice of developers, treating code statements as image patches and comments as texts, and uses contrastive learning to match the semantically-related part between the visual and textual information. Experiments on a large-scale manually-labelled dataset show that our approach can achieve an F1-score around 80%, and such a performance exceeds a heuristic-based baseline to a large extent. We also find that Fosterer can work with a high efficiency, i.e., it only needs 1.5 seconds for inferring the results for a code-comment pair. Furthermore, a user study demonstrates its usability: for 65% cases, its prediction results are considered as useful for improving code understanding. Therefore, our research sheds light on a promising direction for program comprehension.

BACKGROUND: Collagen VI family (COL6A) is a major member of extracellular matrix protein. There is accumulating evidence that COL6A is involved in tumorigenesis and tumor progression. In this study, we performed a systematic analysis of COL6A in pan-cancer based on their molecular features and clinical significance. METHODS: Based on updated public databases, we integrated several bioinformatics analysis methods to investigate the expression levels of COL6A as well as the relationship between their expression and patient survival, immune subtypes, tumor microenvironment, stemness scores, drug sensitivity, and DNA methylation. RESULTS: The expression levels of COL6A members varied in different cancers, suggesting their expression was cancer-dependent. Among COL6A members, COL6A1/2/3 were predicted poor prognosis in specific cancers. Furthermore, COL6A1/2/3 expression levels revealed a clear correlation with immune subtypes, and COL6A1/2/3 were associated with tumor purity, that is, gene expression levels were generally higher in tumors with higher stromal scores and immune scores. COL6A1/2/3 had a significantly negative correlation with RNA stemness scores, and meanwhile they were also related to DNA stemness scores in different degrees. In addition, the expression of COL6A1/2/3 was significantly related to drug sensitivity of cancer cells. Finally, our study revealed that COL6A1/2/3 expression was mainly negatively correlated with gene methylation, and the methylation levels showed remarkable differences in various cancers. CONCLUSIONS: These findings highlight both the similarities and differences in the molecular characteristics of COL6A members in pan-cancer, and provide comprehensive insights for further investigation into the mechanism of COL6A.

Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visual transformer, the cascaded self-attention modules can capture long-distance feature dependencies but unfortunately deteriorate local feature details. In this paper, we propose a hybrid network structure, termed Conformer, to take advantage of convolutional operations and self-attention mechanisms for enhanced representation learning. Conformer roots in the Feature Coupling Unit (FCU), which fuses local features and global representations under different resolutions in an interactive fashion. Conformer adopts a concurrent structure so that local features and global representations are retained to the maximum extent. Experiments show that Conformer, under the comparable parameter complexity, outperforms the visual transformer (DeiT-B) by 2.3% on ImageNet. On MSCOCO, it outperforms ResNet-101 by 3.7% and 3.6% mAPs for object detection and instance segmentation, respectively, demonstrating the great potential to be a general backbone network. Code is available at github.com/pengzhiliang/Conformer.

In many athlete or firefighter training practices, such as firefighter rescue training or football player dribbling, many movement trajectories will be generated. Recording the exercise data of these trainees can replay the training process and help to improve their learning. In the generation of motion trajectory, the judgment of the motion heading matters and attracts lots of attentions. A large amount of researches have focused on the foot-mounted Miniature Inertial Measurement Unit (MIMU), mainly relying on zero-velocity update (ZUPT) to maintain accuracy. However, ZUPT fails to estimate the gyroscope drift errors, causing the heading angle drifts over time. In this paper, we introduce the waist-mounted MIMU for heading judgment based on deep learning algorithms to alleviate the heading angle drift problem. Although the market is more demanding for the waist-mounted module, there are fewer applications due to its insufficient accuracy. In order to improve the heading judgment of waist-mounted model, we propose to use the stacked LSTM model which we prove is powerful to assist the traditional Pedestrian Dead Reckoning (PDR) in the trajectory drawing, and thus is helpful for the heading judgment. Experimental results show that the proposed model has satisfactory performance in heading judgment.